mm/device-public-memory: device memory cache coherent with CPU

Platform with advance system bus (like CAPI or CCIX) allow device memory
to be accessible from CPU in a cache coherent fashion.  Add a new type of
ZONE_DEVICE to represent such memory.  The use case are the same as for
the un-addressable device memory but without all the corners cases.

Link: http://lkml.kernel.org/r/20170817000548.32038-19-jglisse@redhat.com
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: David Nellans <dnellans@nvidia.com>
Cc: Evgeny Baskakov <ebaskakov@nvidia.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mark Hairgrove <mhairgrove@nvidia.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Sherry Cheung <SCheung@nvidia.com>
Cc: Subhash Gutti <sgutti@nvidia.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Bob Liu <liubo95@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 38 insertions, 19 deletions

diff --git a/mm/migrate.c b/mm/migrate.c
index e581253ef330..618aeb5e9cde 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -36,6 +36,7 @@
 #include <linux/hugetlb.h>
 #include <linux/hugetlb_cgroup.h>
 #include <linux/gfp.h>
+#include <linux/pfn_t.h>
 #include <linux/memremap.h>
 #include <linux/userfaultfd_k.h>
 #include <linux/balloon_compaction.h>
@@ -239,10 +240,14 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 		if (is_write_migration_entry(entry))
 			pte = maybe_mkwrite(pte, vma);
 
-		if (unlikely(is_zone_device_page(new)) &&
-		    is_device_private_page(new)) {
-			entry = make_device_private_entry(new, pte_write(pte));
-			pte = swp_entry_to_pte(entry);
+		if (unlikely(is_zone_device_page(new))) {
+			if (is_device_private_page(new)) {
+				entry = make_device_private_entry(new, pte_write(pte));
+				pte = swp_entry_to_pte(entry);
+			} else if (is_device_public_page(new)) {
+				pte = pte_mkdevmap(pte);
+				flush_dcache_page(new);
+			}
 		} else
 			flush_dcache_page(new);
 
@@ -437,12 +442,11 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	void **pslot;
 
 	/*
-	 * ZONE_DEVICE pages have 1 refcount always held by their device
-	 *
-	 * Note that DAX memory will never reach that point as it does not have
-	 * the MEMORY_DEVICE_ALLOW_MIGRATE flag set (see memory_hotplug.h).
+	 * Device public or private pages have an extra refcount as they are
+	 * ZONE_DEVICE pages.
 	 */
-	expected_count += is_zone_device_page(page);
+	expected_count += is_device_private_page(page);
+	expected_count += is_device_public_page(page);
 
 	if (!mapping) {
 		/* Anonymous page without mapping */
@@ -2123,7 +2127,6 @@ out_unlock:
 
 #endif /* CONFIG_NUMA */
 
-
 struct migrate_vma {
 	struct vm_area_struct	*vma;
 	unsigned long		*dst;
@@ -2263,7 +2266,7 @@ again:
 				pfn = 0;
 				goto next;
 			}
-			page = vm_normal_page(migrate->vma, addr, pte);
+			page = _vm_normal_page(migrate->vma, addr, pte, true);
 			mpfn = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE;
 			mpfn |= pte_write(pte) ? MIGRATE_PFN_WRITE : 0;
 		}
@@ -2406,10 +2409,19 @@ static bool migrate_vma_check_page(struct page *page)
 		if (is_device_private_page(page))
 			return true;
 
-		/* Other ZONE_DEVICE memory type are not supported */
-		return false;
+		/*
+		 * Only allow device public page to be migrated and account for
+		 * the extra reference count imply by ZONE_DEVICE pages.
+		 */
+		if (!is_device_public_page(page))
+			return false;
+		extra++;
 	}
 
+	/* For file back page */
+	if (page_mapping(page))
+		extra += 1 + page_has_private(page);
+
 	if ((page_count(page) - extra) > page_mapcount(page))
 		return false;
 
@@ -2647,11 +2659,18 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 	 */
 	__SetPageUptodate(page);
 
-	if (is_zone_device_page(page) && is_device_private_page(page)) {
-		swp_entry_t swp_entry;
-
-		swp_entry = make_device_private_entry(page, vma->vm_flags & VM_WRITE);
-		entry = swp_entry_to_pte(swp_entry);
+	if (is_zone_device_page(page)) {
+		if (is_device_private_page(page)) {
+			swp_entry_t swp_entry;
+
+			swp_entry = make_device_private_entry(page, vma->vm_flags & VM_WRITE);
+			entry = swp_entry_to_pte(swp_entry);
+		} else if (is_device_public_page(page)) {
+			entry = pte_mkold(mk_pte(page, READ_ONCE(vma->vm_page_prot)));
+			if (vma->vm_flags & VM_WRITE)
+				entry = pte_mkwrite(pte_mkdirty(entry));
+			entry = pte_mkdevmap(entry);
+		}
 	} else {
 		entry = mk_pte(page, vma->vm_page_prot);
 		if (vma->vm_flags & VM_WRITE)
@@ -2768,7 +2787,7 @@ static void migrate_vma_pages(struct migrate_vma *migrate)
 					migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
 					continue;
 				}
-			} else {
+			} else if (!is_device_public_page(newpage)) {
 				/*
 				 * Other types of ZONE_DEVICE page are not
 				 * supported.